XAUUSD V05H BUY
Experimental machine-learning BUY model for XAUUSD / Gold.
Model information
- Model ID:
V05H_WF2025_RF_BUY - Strategy ID:
V05H_BUY - Instrument:
XAUUSD - Direction:
BUY - Timeframe:
M5 - Model family:
Random Forest - Inference format:
ONNX - Required features:
830
Decision rule
Current BUY probability rule:
prob_buy >= 0.9391089677810669
If the probability is below the threshold, the strategy returns HOLD.
Trade contract
Direction: BUY
Timeframe: M5
Stop Loss: 1.5 ATR
Take Profit: 2.0 ATR
Maximum Hold: 6 M5 bars
Magic Number: 7300501
Included files
final_rf_buy_model.onnx
feature_order.json
score_distribution.parquet
policy_config.json
model_registry.json
Feature contract
Inputs must follow exactly the feature order defined in:
feature_order.json
Current live validation requires:
expected features = 830
present features = 830
missing features = 0
null after fill = 0
infinite after fill = 0
before inference.
Runtime flow
MT5 M5/M15/H1/H4 data
-> multi-timeframe feature engineering
-> structure / confluence / pattern features
-> 830-feature vector
-> V05H ONNX model
-> BUY probability
-> probability threshold
-> BUY signal or HOLD
Timestamp requirement
Live market timestamps must use consistent UTC semantics.
Broker/server time should not simply be labeled as UTC because session and time-dependent features can otherwise shift.
Intended use
This model is designed to operate independently inside the multi-strategy XAUUSD portfolio framework.
For example, an M15 SELL strategy and this M5 BUY strategy may both generate their own independent positions on an MT5 hedging account.
Risk notice
This repository contains experimental trading research software.
Historical, validation, or backtest performance does not guarantee future profitability. Leveraged trading can result in substantial losses.
Use a demo or paper environment first and independently validate model behavior, execution, spread, commission, slippage, and risk controls.